Thanks to everyone for attending my session on running a Local LLM.
If you have any questions, please feel free to reach out with them. The slides with links embedded is below:
Slides: Running a Local LLM.PPTX
I’ll blog next week on a few of the questions people asked, so if you have anything you want answered, please reach out.
Recently I saw an interesting article, saying that someone could build a general purpose coding agent in 131 lines of Python code. That’s a neat idea, though I’m not sure that this is better than just using Claude Code, especially as the agent still uses the online version of the Claude model from Anthropic to generate code or perform other tasks. There’s a video in the article showing how this code can be used to perform some quick tasks on a computer.
However, the code isn’t specific to Anthropic. It can be used with any LLM, and I started doing just that, with a copy of the code from the article, but modified to use a local AI LLM running under Ollama. You can see my repo and feel free to download and play with it. It’s expecting a local LLM on 11434.
I’m a big fan of local agents for a variety of reasons, but mostly because I know humans tend to do dumb things. Especially with new technology, and maybe even more especially in development areas.
That includes me.
I’ll take shortcuts. I’ll give an agent sysadmin on a dev database to try things. I want to be able to experiment, learn, and see what works. I want to learn how to use tools and fail using them. That’s how I get better. That’s how I get better in sports, in music, and in technology.
And that’s not a project I can take time to work on. I don’t get to dedicate time to just learn and then go back to work. Work never ends. It’s a grinding, constant, continuous treadmill of things I need to deliver to others. I have to learn to experiment around those deliverables when I can find spare moments.
With AI, that means we’ll do things that get InfoSec teams to cringe. I get the concerns over data transiting networks and going to who-knows-where to be used who-knows-how-by-others. I appreciate business subscriptions that guarantee that data won’t be used, but I also want extra safeguards at times. That means local models. Not necessarily on my laptop, but in my data center.
Plus, that way I (or my org) can control the costs and manage expectations.
I hope local models and local agents catch on, I hope more vendors support them and more organizations are willing to run them. Even in something like AWS Bedrock or Azure Open AI or Vertex AI. Then I can rent the latest and greatest hardware, but have more control over how my organization uses it.
Steve Jones
Listen to the podcast at Libsyn, Spotify, or iTunes.
Note, podcasts are only available for a limited time online.
In the last year I’ve seen a lot of statements about data and sovereignty between countries. While there have been concerns in the past, there seems to be more worry around the world with AI services primarily being run by, and hosted by, US companies. Plenty of my customers at Redgate Software have concerns over our ability to see data when we run AI models, though we don’t store the data. Once the session ends, the data is discarded by policy
Recently I saw a piece about France trying to rid itself of the reliance on US technology, specifically the Windows OS from Microsoft. They are looking to move to their own version of Linux, as well as a number of open source software packages. This quote was fascinating to me: “We can no longer accept that our data, our infrastructure, and our strategic decisions depend on solutions whose rules, pricing, evolution, and risks we do not control.”
With AI being added to lots of software, including OSes, I suspect that other countries might look to follow France. I know the EU is looking to move, and Brazil has been trying to use more Linux and OSS for decades. While I find Windows works well, I completely understand wanting to move, especially in this era where many software packages are web-based and can run on a different OS.
SQL Server runs on Linux, and half of my testing is on Linux, since I run SQL Server in a container on my laptop. My desktop still has a native Windows install, but I find it easy to port almost all code back and forth between the two versions. While I understand others might have a preference for PostgreSQL or MySQL or some other OSS platform, I think SQL Server provides a great value for many organizations. I also think it’s incredibly hard to port your software and data from one database platform to another.
I do wonder if governments or organizations outside the US that look to leave Windows will also look to leave SQL Server. It’s one thing to move away from the OS and software like Office. A little training will get most users productive on a new system in a relatively short time. Moving a software application and its database is a much larger challenge.
I expect SQL Server to remain incredibly popular for many years, and with the ability to configure the new AI capabilities to use your own models, I am not sure a country that wants to reduce their reliance on US technology will choose to do so for their databases. They will likely start elsewhere and continue to use SQL Server for years.
Steve Jones
Listen to the podcast at Libsyn, Spotify, or iTunes.
Note, podcasts are only available for a limited time online.
There was a post on X recently from a founder in the EU about an engineer using Claude and ChatGPT to build a feature. I am not sure how true these posts are or if they are designed to just create engagement, but it’s still an interesting topic. The part that makes me think is that (supposedly) the engineer was fired because their “data” (code) was sent to American servers. The code was then deleted and the feature will be built without AI.
First, read some of the responses before you form an opinion. There are some funny ones in there. There are a few I think are overblown and silly, and I skim past them. Someone is always more upset than I am, and more than I think they rationally should be, so I tend to let their outrage flow by me.
There are two interesting things here. First, the debate about sending data to America. There certainly is some cause for concern here if data is being sent to a place outside of the EU where GDPR rules might apply. There possibly could be some legal issue here, though I doubt some of the responses about all code being compromised are an issue here. I don’t think code is PII, though if it were re-used or appears in AI output, perhaps investors could sue this company.
The second thing here is whether someone should be fired for doing this. There might be a policy and some training about not doing this, and in that case, perhaps the person should be fired. However, I find this kind of thing happening too often, and it’s the type of thing that has happened before AI where people used outside sources (SQL Server Central, Stack Overflow, etc.) to post code in a question and get an answer. And then often use that code without changing or testing it.
Is this rational? Some people might say yes, some no, many unsure. In the past, before AI, what would you think? To me, sometimes there have been solutions engineers have found but couldn’t use code written by someone else. There are real IP/copyright concerns here. You could rebuild the solution, rewriting the code, which in some sense is what Google did with Java APIs and successfully defended that effort. If another human or an AI gives you code, can you rewrite that code, keeping the same idea for the solution?
I think that in most cases this is acceptable. I use AI for a lot of things and I throw away a lot of AI output, but it often gets me started down a path, whether in writing, coding, or something else.
Who was more irresponsible here, the founder or the engineer? I think the former.
Steve Jones
Listen to the podcast at Libsyn, Spotify, or iTunes.
Note, podcasts are only available for a limited time online.
